Video Panoptic Segmentation

TL;DR

This paper introduces video panoptic segmentation, a new task combining semantic and instance segmentation across video frames, along with datasets, a novel network, and evaluation metrics, achieving state-of-the-art results.

Contribution

It proposes the first video panoptic segmentation task, creates new datasets, and develops VPSNet, a model that jointly predicts segmentation and tracking in videos.

Findings

Effective datasets for video panoptic segmentation

VPSNet achieves state-of-the-art results on Cityscapes and VIPER

Proposed VPQ metric evaluates segmentation and tracking quality

Abstract

Panoptic segmentation has become a new standard of visual recognition task by unifying previous semantic segmentation and instance segmentation tasks in concert. In this paper, we propose and explore a new video extension of this task, called video panoptic segmentation. The task requires generating consistent panoptic segmentation as well as an association of instance ids across video frames. To invigorate research on this new task, we present two types of video panoptic datasets. The first is a re-organization of the synthetic VIPER dataset into the video panoptic format to exploit its large-scale pixel annotations. The second is a temporal extension on the Cityscapes val. set, by providing new video panoptic annotations (Cityscapes-VPS). Moreover, we propose a novel video panoptic segmentation network (VPSNet) which jointly predicts object classes, bounding boxes, masks, instance id tracking, and semantic segmentation in video frames. To provide appropriate metrics for this task, we propose a video panoptic quality (VPQ) metric and evaluate our method and several other baselines. Experimental results demonstrate the effectiveness of the presented two datasets. We achieve state-of-the-art results in image PQ on Cityscapes and also in VPQ on Cityscapes-VPS and VIPER datasets. The datasets and code are made publicly available.